Vision-Based Detection and Tracking of a Moving Target for a Smart Car

Guo Yuqing; Guo Yanning; Xu Hang; Feng Zhen

doi:10.1109/ICIVC.2018.8492729

Vision-Based Detection and Tracking of a Moving Target for a Smart Car

Guo Yuqing
, Guo Yanning
, Xu Hang
, Feng Zhen

School of Astronautics

Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Scopus citations

Abstract

In this paper, vision-based detection and tracking of a moving target for a smart car system is proposed and implemented on a smart car loaded with raspberry pi. In target detection, FLANN is used to replace the traditional violence matching method, which significantly increases the quickness and accuracy of feature matching. In our system, ultrasonic data are used to solve scale ambiguity of the monocular camera. To address multiple interfering objects in the initial field of view, we propose the idea of initial hypothesis frame. During the tracking process, the target trajectory is estimated and predicted with the unscented Kalman filter to solve the loss or occlusion of the target. In the controller design, single neuron adaptive PID control is adopted. All these functions and algorithms are implemented on a raspberry pi.

Original language	English
Title of host publication	2018 3rd IEEE International Conference on Image, Vision and Computing, ICIVC 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	586-591
Number of pages	6
ISBN (Electronic)	9781538649916
DOIs	https://doi.org/10.1109/ICIVC.2018.8492729
State	Published - 15 Oct 2018
Event	3rd IEEE International Conference on Image, Vision and Computing, ICIVC 2018 - Chongqing, China Duration: 27 Jun 2018 → 29 Jun 2018

Publication series

Name	2018 3rd IEEE International Conference on Image, Vision and Computing, ICIVC 2018

Conference

Conference	3rd IEEE International Conference on Image, Vision and Computing, ICIVC 2018
Country/Territory	China
City	Chongqing
Period	27/06/18 → 29/06/18

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 16 Peace, Justice and Strong Institutions

Keywords

Pose estimation
Raspberry pi
Target detection and tracking
Unscented Kalman filter

Access to Document

10.1109/ICIVC.2018.8492729

Cite this

Yuqing, G., Yanning, G., Hang, X., & Zhen, F. (2018). Vision-Based Detection and Tracking of a Moving Target for a Smart Car. In 2018 3rd IEEE International Conference on Image, Vision and Computing, ICIVC 2018 (pp. 586-591). Article 8492729 (2018 3rd IEEE International Conference on Image, Vision and Computing, ICIVC 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIVC.2018.8492729

@inproceedings{3d27c2fcb63d433bb6cf32ee76f3357a,

title = "Vision-Based Detection and Tracking of a Moving Target for a Smart Car",

abstract = "In this paper, vision-based detection and tracking of a moving target for a smart car system is proposed and implemented on a smart car loaded with raspberry pi. In target detection, FLANN is used to replace the traditional violence matching method, which significantly increases the quickness and accuracy of feature matching. In our system, ultrasonic data are used to solve scale ambiguity of the monocular camera. To address multiple interfering objects in the initial field of view, we propose the idea of initial hypothesis frame. During the tracking process, the target trajectory is estimated and predicted with the unscented Kalman filter to solve the loss or occlusion of the target. In the controller design, single neuron adaptive PID control is adopted. All these functions and algorithms are implemented on a raspberry pi.",

keywords = "Pose estimation, Raspberry pi, Target detection and tracking, Unscented Kalman filter",

author = "Guo Yuqing and Guo Yanning and Xu Hang and Feng Zhen",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 3rd IEEE International Conference on Image, Vision and Computing, ICIVC 2018 ; Conference date: 27-06-2018 Through 29-06-2018",

year = "2018",

month = oct,

day = "15",

doi = "10.1109/ICIVC.2018.8492729",

language = "英语",

series = "2018 3rd IEEE International Conference on Image, Vision and Computing, ICIVC 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "586--591",

booktitle = "2018 3rd IEEE International Conference on Image, Vision and Computing, ICIVC 2018",

address = "美国",

}

Yuqing, G, Yanning, G, Hang, X & Zhen, F 2018, Vision-Based Detection and Tracking of a Moving Target for a Smart Car. in 2018 3rd IEEE International Conference on Image, Vision and Computing, ICIVC 2018., 8492729, 2018 3rd IEEE International Conference on Image, Vision and Computing, ICIVC 2018, Institute of Electrical and Electronics Engineers Inc., pp. 586-591, 3rd IEEE International Conference on Image, Vision and Computing, ICIVC 2018, Chongqing, China, 27/06/18. https://doi.org/10.1109/ICIVC.2018.8492729

Vision-Based Detection and Tracking of a Moving Target for a Smart Car. / Yuqing, Guo; Yanning, Guo; Hang, Xu et al.
2018 3rd IEEE International Conference on Image, Vision and Computing, ICIVC 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 586-591 8492729 (2018 3rd IEEE International Conference on Image, Vision and Computing, ICIVC 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Vision-Based Detection and Tracking of a Moving Target for a Smart Car

AU - Yuqing, Guo

AU - Yanning, Guo

AU - Hang, Xu

AU - Zhen, Feng

PY - 2018/10/15

Y1 - 2018/10/15

N2 - In this paper, vision-based detection and tracking of a moving target for a smart car system is proposed and implemented on a smart car loaded with raspberry pi. In target detection, FLANN is used to replace the traditional violence matching method, which significantly increases the quickness and accuracy of feature matching. In our system, ultrasonic data are used to solve scale ambiguity of the monocular camera. To address multiple interfering objects in the initial field of view, we propose the idea of initial hypothesis frame. During the tracking process, the target trajectory is estimated and predicted with the unscented Kalman filter to solve the loss or occlusion of the target. In the controller design, single neuron adaptive PID control is adopted. All these functions and algorithms are implemented on a raspberry pi.

AB - In this paper, vision-based detection and tracking of a moving target for a smart car system is proposed and implemented on a smart car loaded with raspberry pi. In target detection, FLANN is used to replace the traditional violence matching method, which significantly increases the quickness and accuracy of feature matching. In our system, ultrasonic data are used to solve scale ambiguity of the monocular camera. To address multiple interfering objects in the initial field of view, we propose the idea of initial hypothesis frame. During the tracking process, the target trajectory is estimated and predicted with the unscented Kalman filter to solve the loss or occlusion of the target. In the controller design, single neuron adaptive PID control is adopted. All these functions and algorithms are implemented on a raspberry pi.

KW - Pose estimation

KW - Raspberry pi

KW - Target detection and tracking

KW - Unscented Kalman filter

UR - https://www.scopus.com/pages/publications/85056510456

U2 - 10.1109/ICIVC.2018.8492729

DO - 10.1109/ICIVC.2018.8492729

M3 - 会议稿件

AN - SCOPUS:85056510456

T3 - 2018 3rd IEEE International Conference on Image, Vision and Computing, ICIVC 2018

SP - 586

EP - 591

BT - 2018 3rd IEEE International Conference on Image, Vision and Computing, ICIVC 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 3rd IEEE International Conference on Image, Vision and Computing, ICIVC 2018

Y2 - 27 June 2018 through 29 June 2018

ER -

Yuqing G, Yanning G, Hang X, Zhen F. Vision-Based Detection and Tracking of a Moving Target for a Smart Car. In 2018 3rd IEEE International Conference on Image, Vision and Computing, ICIVC 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 586-591. 8492729. (2018 3rd IEEE International Conference on Image, Vision and Computing, ICIVC 2018). doi: 10.1109/ICIVC.2018.8492729

Vision-Based Detection and Tracking of a Moving Target for a Smart Car

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this